Skip to main content
Recursion Managed Agents runs agents that need a sandbox, tools, and more than one model turn. Each session keeps a durable record that you can inspect, continue, or grade.
Recursion Managed Agents is designed around persistent, stateful sessions. Agent sessions may remain active over extended periods, resume after interruptions, and retain conversation history, sandbox state, and generated outputs on the server.Because Managed Agents relies on this server-side state, it is currently not supported for customers requiring Zero Data Retention (ZDR) or HIPAA Business Associate Agreement (BAA) coverage. Customers with an active BAA or ZDR arrangement, or with a use case that requires either, cannot use Recursion Managed Agents at this time.

​
What do you want to do?

Run your first graded task

Create an API key, an environment, and an agent, then read a grader’s verdict. About 10 minutes.

Understand the model

See how agents, environments, sessions, vaults, and outcomes fit together.

Build in the console

Find the screen for each setup, launch, and inspection task.

Call the API

Install an SDK, authenticate, and learn the retry and paging rules.

Connect your apps

Let agents work in 164+ apps, choose their tools, or add any MCP server.

Split work across agents

Delegate to subagents or let a team share a task board.

Automate sessions

Run agents on a schedule or when Slack, GitHub, or a webhook sends an event.

Give agents memory

Let agents learn from past sessions and read your curated knowledge.

Connect a coding agent

Let your AI coding agent read these docs and call the API for you.

Fix a problem

Match an error code or symptom to its cause and fix.

​
What you can do

​
How it fits together

You start a session with an agent and an environment. The session freezes both, so later edits never change work in progress. The agent works in its sandbox, every step lands in the event log, and a grader decides when the work meets your rubric. How it works explains each piece.

​
When to use Managed Agents

Use Managed Agents when the work needs one or more of these:
  • Several model turns and tool calls.
  • A shell, files, package installation, or a browser in a sandbox.
  • Work in other systems, such as Salesforce, Jira, or Snowflake, an API with a token, or an MCP server.
  • A rubric that sends incomplete work back for revision.
  • A durable record you can review, audit, or continue later.
For a single model response with no tools or sandbox, call the model directly instead.

​
Next steps

Quickstart

Run a graded task in the console or with code.

How it works

Learn the concepts and see the session, credential, and grading flows.

API conventions

Set up an SDK and learn the shared request rules.

Glossary

Look up any term used in these docs.